DATA PROCESSING

B. Data Processing with SPSS for Windows

SPSS (Statistical Program for Social Science) is a statistical program package that is useful
for processing and analyzing research data easily and quickly. The capabilities that can be
obtained from SPSS include processing all forms of data files, modifying data, creating
tabulations in the form of frequency distributions, descriptive statistical analysis, simple
and complex advanced statistical analysis, creating graphs, etc. The development of the
SPSS program was very fast, starting from the SPSS/PC+ program (still under DOS) then
developing into SPSS for Window from version 6 and continuing to develop until now it
has entered version 26.

Call & Open SPSS

The first time you have to make sure that the SPSS for Windows program is installed on
your computer. To call the SPSS program you can do it in two ways:
1. If the SPSS icon appears on the computer's first display, then click with the mouse on
the icon twice
2. If there is no SPSS icon on the computer screen, then click Start, select Program Files
and highlight SPSS and double click.
In its operations, SPSS recognizes 2 main types of windows, namely:
1. SPSS Data Editor
This window contains a display of the data that we process and analyze using a
spreadsheet-like display (such as an Excel display).

2. SPSS output
The processed results (analysis results) that you carry out will be displayed in the
output window. This window is a text editor, meaning you can edit the displayed
analysis results.

Data Structures in SPSS

In order to be processed with SPSS, data must have a certain structure, format and type.
In SPSS (and what is common in other programs), the processed data is collected based
on columns and rows. Each column represents one variable, for example each question
on a questionnaire represents one variable. Each row of data is called a case
(case/respondent).
 Variable Name Age Weight
Case Jhonson 21 38
Cristiano 25 55

The example above shows that there are 3 variables (name, age, weight) and 2
cases/respondents

Main View of SPSS for Window

After the SPSS program is called, the SPSS for Window logo will appear on the screen, wait
a moment until the logo disappears, then the main SPSS display will appear on the
monitor screen as follows:

The SPSS for Window work system is controlled by the menu (menu bar). The menu bar
is located at the top in the following order from left to right: File, Edit, Data, Transform,
Statistics, Graph, Utilities, Window, Help.
• File: used to create a new data file, open a saved data file (sav extension), or read
data files from other programs, such as dbase, excel, etc.
• Edit: used to modify, copy, delete, find and replace data.
• Data: used to create/define variable names, retrieve/analyze some data, combine
data.
• Transform : used for transformation/modification of data such as grouping
variables, creating new variables from multiplication/addition of existing
variables, etc.
 • Statistics : used to select various statistical procedures, from simple statistics
(descriptive) to complex statistical analysis (multivariate).
• Graph: used to create graphs including bar graphs, pie, line, histogram, scatter
plot, etc.
• Utilities: used to display various information about the contents of the file.
• Window: used to move between windows, for example from the Data window to
the Output window.
• Help: contains information on how to use various facilities in SPSS.

Entry Data

Data entry can be directly done in the Data Editor. The Data Editor has a spreadsheet-like
display form (such as Excel) that is used as a facility for entering/filling in data. There are
three things to pay attention to:
1. Rows indicate cases/respondents
2. Columns indicate variables
3. Cells are the intersections between columns and rows indicating values/data.

As an example, data entry will be carried out on the characteristics of mothers and babies:
baby's number, job, and weight.
Number Job status Baby's Weight (kg)
( 1=work, 2=not work)
1 1 2,7
2 2 3,0
3 1 3,4
4 1 3,1
5 2 3,6

There are two ways to enter data directly, especially in defining variables, namely:
1. Enter data first then define variables.
For this method, the following steps must be taken:
a. From the main menu, data can be directly entered into the cells as shown in the
image below
b. The next step is to rename the variables accordingly. For example, the sequence
of variable names is number, work and weight (example data above), then click
on the variable view so that it appears as shown in the following image:
 c. If you want to see the effect of changing variables, click data view so a display like
the image below will appear:

2. Defining variables first, then entering data.

The second way is to define the variable name first and then fill in the data. The steps that
must be taken are as follows:
a. Activate the view variable (in the bottom right corner).
b. Fill in the variable name in the Name column as shown below:

One variable represents/symbolizes one question. In order not to encounter difficulties

in creating variable names, the following will explain the terms/requirements for variable
names:
• Variable names contain a maximum of 8 letters
• Variable names cannot contain spaces
• No variable names are the same (no 2 variables can have the same name)
 1) Set the Type column as needed by clicking on the cell with the variable name, select
the appropriate data type. Click the OK button to continue or Cancel if you want to
cancel.

2) Column Width can be set according to the required width of the data. You can adjust
it through the data view, just like setting the column width in Microsoft Excel or Lotus
123. This column is used to determine how many digits or characters of data can be
entered.
3) The Decimal column can be filled if the data in that column is of Numeric type only.
4) The Label column is used to provide an explanation of the variable. Enter the
identification number (in this exercise).
5) The Values column is used to describe individual values with their labels.
6) The Missing column is used if the data to be processed contains missing or missing
data. That is if in a data file there is data that is not recorded due to one thing. For
example, the Missing column is filled with a '*' sign, so if the data entered is a '*' in
this variable, it means that the data does not exist.
7) The Colums column is used to determine the width of the data column.
8) The Align column shows how the data looks left, right or center aligned.
9) The Measure column shows the type of data measurement whether the data type is
Scale(Interval or Ratio), Nominal or Ordinal.

3. Do the same method (2-2i) for creating a job status variable.

a. Create a job status variable with a work variable name, with a numeric type and the
number of decimal places (decimal places) removed and filled with 0.
b. The next step is to provide labels and value labels. There is a slight difference in the
working variable, the manufacturing step for the value label must be filled because the
data from the work variable are codes, namely 1=working and 2=not working, so it is
necessary to define these codes
How to make :
1) Click the Label option, fill in the mother's employment status.
 2) Click the Value option, in the value box type 1, and in the value label box type work.
3) Click the Add button so that below the words 1=”working” will appear
4) Do the same thing for value label 2, enter it and it doesn't work, press the Add button.
And finally it looks as follows:

4. Next, create a baby weight variable.

a. Create a baby weight variable with the variable name weight with numeric type and
decimal number 1.
b. Click the Label option, enter the baby's weight. Value Label leave blank

5. After the three variables (number, work, weight) have been filled in with complete data,
the display will look as follows: